Multivariable adaptive identification and control for artificial pancreas systems

Distribution-based sub-population selection (DSPS): A method for in-silico reproduction of clinical trials outcomes

Diabetes presents a significant challenge to healthcare due to the short- and long-term complications associated with poor blood sugar control. Computer simulation platforms have emerged as promising tools for advancing diabetes therapy by simulating patient responses to treatments in a virtual environment. The University of Virginia Virtual Lab (UVLab) is a new simulation platform engineered to mimic the metabolic behavior of individuals with type 2 diabetes (T2D) using a mathematical model of glucose homeostasis in T2D and a large population of 6062 virtual subjects. This work proposes a statistical method - the Distribution-based sub-population selection (DSPS) method - for selecting subsets of virtual subjects from this large initial pool, ensuring that the selected group possesses the desired characteristics necessary to reproduce and predict the outcomes of a clinical trial. DSPS formulates the sub-population selection as a linear programming problem, identifying the largest virtual cohort to closely resemble the statistical properties (moments) of key outcomes from real-world clinical trials. The method was applied to the insulin degludec arm of a 26-week phase 3 clinical trial, evaluating the efficacy and safety of insulin degludec and liraglutide combination therapy. DSPS selected a sub-population that mirrored clinical trial data across key metrics, including glycemic efficacy, insulin dosages, and cumulative hypoglycemia events, with a relative sum of square errors of 0.33 and a percentage error of 1.07 %. This approach bridges the gap between large population simulation platforms and clinical trials, enabling the selection of virtual sub-populations with specific properties required for targeted studies.

Evaluation of machine learning-based regression techniques for prediction of diabetes levels fluctuations

Middle-Aged and Elderly people today face a variety of health problems as a result of their modern lifestyle, which includes increased work stress, less physical activity, and altered food habits. Because of Complications arising, diabetes has become one of the most frequent, severe, and fatal illnesses around the world. Therefore, inaccurate measurements of blood glucose levels can seriously damage vital organs. Several strategies for long-term glucose prediction have been proposed in the literature. Unfortunately, these methods require the patient to identify their daily activities, which can be error-prone, such as meal intake, insulin injection, and emotional aspects. This paper suggests using continuous glucose monitoring (CGM) of 14733 patients, with three assistance factors to predict blood glucose levels independently of other parameters, hence reducing the burden on the patients. To support this an Artificial Neural Network (ANN), Binary Decision Tree (BDT), Linear Regression (LR), Boosting Regression Tree Ensemble (BSTE), Linear Regression with Stochastic Gradient Descent (LRSGD), Stepwise (SW), Support Vector Machine (SVM), and Gaussian process regression (GPR) were investigated. The result indicated that The highest classification accuracy of (92.58%) has been achieved by BDT followed by BSTE (92.04%) and GPR (88.59%). The obtained average of root means square error (MSE) was 1.64, 1.67, 1.69, mg/dL for prediction horizon (PH) respectively to GPR, BSTE, and ANN.

Developing the UVA/Padova Type 1 Diabetes Simulator: Modeling, Validation, Refinements, and Utility

Arguably, diabetes mellitus is one of the best quantified human conditions. In the past 50 years, the metabolic monitoring technologies progressed from occasional assessment of average glycemia via HbA1c, through episodic blood glucose readings, to continuous glucose monitoring (CGM) producing data points every few minutes. The high-temporal resolution of CGM data enabled increasingly intensive treatments, from decision support assisting insulin injection or oral medication, to automated closed-loop control, known as the "artificial pancreas." Throughout this progress, mathematical models and computer simulation of the human metabolic system became indispensable for the technological progress of diabetes treatment, enabling every step, from assessment of insulin sensitivity via the now classic Minimal Model of Glucose Kinetics, to in silico trials replacing animal experiments, to automated insulin delivery algorithms. In this review, we follow these developments, beginning with the Minimal Model, which evolved through the years to become large and comprehensive and trigger a paradigm change in the design of diabetes optimization strategies: in 2007, we introduced a sophisticated model of glucose-insulin dynamics and a computer simulator equipped with a "population" of N = 300 in silico "subjects" with type 1 diabetes. In January 2008, in an unprecedented decision, the Food and Drug Administration (FDA) accepted this simulator as a substitute to animal trials for the pre-clinical testing of insulin treatment strategies. This opened the field for rapid and cost-effective development and pre-clinical testing of new treatment approaches, which continues today. Meanwhile, animal experiments for the purpose of designing new insulin treatment algorithms have been abandoned.

Adaptive Personalized Prior-Knowledge-Informed Model Predictive Control for Type 1 Diabetes

This work considers the problem of adaptive prior-informed model predictive control (MPC) formulations that explicitly incorporate prior knowledge in the model development and is robust to missing data in the output measurements. The proposed prediction model is based on a latent variables model to extract glycemic dynamics from highly-correlated data and incorporates prior knowledge of exponential stability to improve the prediction ability. Missing data structures are formulated to enable model predictions when output measurements are missing for short periods of time. Based on the latent variables model, the MPC strategy and adaptive rules are developed to automatically tune the aggressiveness of the MPC. The adaptive prior-knowledge-informed MPC is evaluated with computer simulations for the control of blood glucose concentrations in people with Type 1 diabetes (T1D) using simulated virtual patients. Due to the variability among people with T1D, the hyperparameters of the prior-knowledge-informed model are personalized to individual subjects. The percentage of time spent in the target range is 76.48% when there are no missing data and 76.52% when there are missing data episodes lasting up to 30 mins (6 samples). Incorporating the adaptive rules further improves the percentage of time in target range to 84.58% and 84.88% for cases with no missing data and missing data, respectively. The proposed adaptive prior-informed MPC formulation provides robust, effective, and safe regulation of glucose concentration in T1D despite disturbances and missing measurements.

In-silico evaluation of an artificial pancreas achieving automatic glycemic control in patients with type 1 diabetes

Artificial pancreas (AP) is a useful tool for maintaining the blood glucose (BG) of patients with type 1 diabetes (T1D) within the euglycemic range. An intelligent controller has been developed based on general predictive control (GPC) for AP. This controller exhibits good performance with the UVA/Padova T1D mellitus simulator approved by the US Food and Drug Administration. In this work, the GPC controller was further evaluated under strict conditions, including a pump with noise and error, a CGM sensor with noise and error, a high carbohydrate intake, and a large population of 100 in-silico subjects. Test results showed that the subjects are in high risk for hypoglycemia. Thus, an insulin on board (IOB) calculator, as well as an adaptive control weighting parameter (AW) strategy, was introduced. The percentage of time spent in euglycemic range of the in-silico subjects was 86.0% ± 5.8%, and the patient group had a low risk of hypoglycemia with the GPC+IOB+AW controller. Moreover, the proposed AW strategy is more effective in hypoglycemia prevention and does not require any personalized data compared with the IOB calculator. Thus, the proposed controller realized an automatic control of the BG of patients with T1D without meal announcements and complex user interaction.

Internal model control based module for the elimination of meal and exercise announcements in hybrid artificial pancreas systems

BACKGROUND AND OBJECTIVES

Hybrid artificial pancreas systems outperform current insulin pump therapies in blood glucose regulation in type 1 diabetes. However, subjects still have to inform the system about meals intake and exercise to achieve reasonable control. These patient announcements may result in overburden and compromise controller performance if not provided timely and accurately. Here, a hybrid artificial pancreas is extended with an add-on module that releases subjects from meals and exercise announcements.

METHODS

The add-on module consists of an internal-model controller that generates a "virtual" control action to compensate for disturbances. This "virtual" action is converted into insulin delivery, rescue carbohydrates suggestions, or insulin-on-board limitations, depending on a switching logic based on glucose measurements and predictions. The controller parameters are tuned by optimization and then related to standard parameters from the open-loop therapy. This module is implemented in a hybrid artificial pancreas system proposed by our research group for validation. This hybrid system extended with the add-on module is compared with the hybrid controller with carbohydrate counting errors (hybrid) and the hybrid controller with an alternative unannounced meal compensation module based on a meal detection algorithm (meal detector). The validation used the educational version of the UVa/Padova simulator to simulate the three controllers under two scenarios: one with only meals and another with meals and exercise. The exercise was modeled as a temporal increase of the insulin sensitivity resulting in the glucose drop usually related to an aerobic exercise.

RESULTS

For the scenario with only meals, the three controllers achieved similar time in range (proposed: 85.1 [77.9,88.1]%, hybrid: 84.0 [75.9,86.4]%, meal detector: 81.9 [79.3,83.8]%, median [interquartile range]) with low time in moderate hypoglycemia. Under the scenario with meals and exercise, the proposed module reduces 4.61% the time in hypoglycemia achieved with the other controllers, suggesting an acceptable amount of rescues (27.2 [23.7, 31.0] g).

CONCLUSIONS

The proposed add-on module achieved promising results: it outperformed the meal-detector-based controller, even achieving a postprandial performance as good as the hybrid controller (with carbohydrate counting errors). Also, the rescue suggestion feature of the module mitigated exercise-induced hypoglycemia with admissible rescue amounts.

Integrating Multiple Inputs Into an Artificial Pancreas System: Narrative Literature Review

BACKGROUND

Type 1 diabetes (T1D) is a chronic autoimmune disease in which a deficiency in insulin production impairs the glucose homeostasis of the body. Continuous subcutaneous infusion of insulin is a commonly used treatment method. Artificial pancreas systems (APS) use continuous glucose level monitoring and continuous subcutaneous infusion of insulin in a closed-loop mode incorporating a controller (or control algorithm). However, the operation of APS is challenging because of complexities arising during meals, exercise, stress, sleep, illnesses, glucose sensing and insulin action delays, and the cognitive burden. To overcome these challenges, options to augment APS through integration of additional inputs, creating multi-input APS (MAPS), are being investigated.

OBJECTIVE

The aim of this survey is to identify and analyze input data, control architectures, and validation methods of MAPS to better understand the complexities and current state of such systems. This is expected to be valuable in developing improved systems to enhance the quality of life of people with T1D.

METHODS

A literature survey was conducted using the Scopus, PubMed, and IEEE Xplore databases for the period January 1, 2005, to February 10, 2020. On the basis of the search criteria, 1092 articles were initially shortlisted, of which 11 (1.01%) were selected for an in-depth narrative analysis. In addition, 6 clinical studies associated with the selected studies were also analyzed.

RESULTS

Signals such as heart rate, accelerometer readings, energy expenditure, and galvanic skin response captured by wearable devices were the most frequently used additional inputs. The use of invasive (blood or other body fluid analytes) inputs such as lactate and adrenaline were also simulated. These inputs were incorporated to switch the mode of the controller through activity detection, directly incorporated for decision-making and for the development of intermediate modules for the controller. The validation of the MAPS was carried out through the use of simulators based on different physiological models and clinical trials.

CONCLUSIONS

The integration of additional physiological signals with continuous glucose level monitoring has the potential to optimize glucose control in people with T1D through addressing the identified limitations of APS. Most of the identified additional inputs are related to wearable devices. The rapid growth in wearable technologies can be seen as a key motivator regarding MAPS. However, it is important to further evaluate the practical complexities and psychosocial aspects associated with such systems in real life.

Incorporating Prior Information in Adaptive Model Predictive Control for Multivariable Artificial Pancreas Systems

BACKGROUND

Adaptive model predictive control (MPC) algorithms that recursively update the glucose prediction model are shown to be promising in the development of fully automated multivariable artificial pancreas systems. However, the recursively updated glycemic prediction models do not explicitly consider prior knowledge in the identification of the model parameters. Prior information of the glycemic effects of meals and physical activity can improve model accuracy and yield better glycemic control algorithms.

METHODS

A glucose prediction model based on regularized partial least squares (rPLS) method where the prior information is encoded as the regularization term is developed to provide accurate predictions of the future glucose concentrations. An adaptive MPC is developed that incorporates dynamic trajectories for the glucose setpoint and insulin dosing constraints based on the estimated plasma insulin concentration (PIC). The proposed adaptive MPC algorithm is robust to disturbances caused by unannounced meals and physical activities even in cases with missing glucose measurements. The effectiveness of the proposed adaptive MPC based on rPLS is investigated with in silico subjects of the multivariable glucose-insulin-physiological variables simulator (mGIPsim).

RESULTS

The efficacy of the proposed adaptive MPC strategy in regulating the blood glucose concentration (BGC) of people with T1DM is assessed using the average percent time in range (TIR) for glucose, defined as 70 to 180 mg/dL inclusive, and the average percent time in hypoglycemia (<70 and >54 mg/dL) and level 2 hypoglycemia (≤54 mg/dL). The TIR for a cohort of 20 virtual subjects of mGIPsim is 81.9% ± 7.4% (with no hypoglycemia or severe hypoglycemia) for the proposed MPC compared with 73.9% ± 7.6% (0.2% ± 0.1% in hypoglycemia and 0.1% ± 0.1% in level 2 hypoglycemia) for an MPC based on a recursive autoregressive exogenous (ARX) model.

CONCLUSIONS

The adaptive MPC algorithm that incorporates prior knowledge in the recursive updating of the glucose prediction model can contribute to the development of fully automated artificial pancreas systems that can mitigate meal and physical activity disturbances.

Prior Informed Regularization of Recursively Updated Latent-Variables-Based Models with Missing Observations

Many data-driven modeling techniques identify locally valid, linear representations of time-varying or nonlinear systems, and thus the model parameters must be adaptively updated as the operating conditions of the system vary, though the model identification typically does not consider prior knowledge. In this work, we propose a new regularized partial least squares (rPLS) algorithm that incorporates prior knowledge in the model identification and can handle missing data in the independent covariates. This latent variable (LV) based modeling technique consists of three steps. First, a LV-based model is developed on the historical time series data. In the second step, the missing observations in the new incomplete data sample are estimated. Finally, the future values of the outputs are predicted as a linear combination of estimated scores and loadings. The model is recursively updated as new data are obtained from the system. The performance of the proposed rPLS and rPLS with exogenous inputs (rPLSX) algorithms are evaluated by modeling variations in glucose concentration (GC) of people with Type 1 diabetes (T1D) in response to meals and physical activities for prediction windows up to one hour, or 12 sampling instances, into the future. The proposed rPLS family of GC prediction models are evaluated with both in-silico and clinical experiment data and compared with the performance of recursive time series and kernel-based models. The root mean squared error (RMSE) with simulated subjects in the multivariable T1D simulator where physical activity effects are incorporated in GC variations are 2.52 and 5.81 mg/dL for 30 and 60 mins ahead predictions (respectively) when information for all meals and physical activities are used, increasing to 2.70 and 6.54 mg/dL (respectively) when meals and activities occurred, but the information is with-held from the modeling algorithms. The RMSE is 10.45 and 14.48 mg/dL for clinical study with prediction horizons of 30 and 60 mins, respectively. The low RMSE values demonstrate the effectiveness of the proposed rPLS approach compared to the conventional recursive modeling algorithms.

Activity detection and classification from wristband accelerometer data collected on people with type 1 diabetes in free-living conditions

This paper introduces methods to estimate aspects of physical activity and sedentary behavior from three-axis accelerometer data collected with a wrist-worn device at a sampling rate of 32 [Hz] on adults with type 1 diabetes (T1D) in free-living conditions. In particular, we present two methods able to detect and grade activity based on its intensity and individual fitness as sedentary, mild, moderate or vigorous, and a method that performs activity classification in a supervised learning framework to predict specific user behaviors. Population results for activity level grading show multi-class average accuracy of 99.99%, precision of 98.0 ± 2.2%, recall of 97.9 ± 3.5% and F1 score of 0.9 ± 0.0. As for the specific behavior prediction, our best performing classifier, gave population multi-class average accuracy of 92.43 ± 10.32%, precision of 92.94 ± 9.80%, recall of 92.20 ± 10.16% and F1 score of 92.56 ± 9.94%. Our investigation showed that physical activity and sedentary behavior can be detected, graded and classified with good accuracy and precision from three-axial accelerometer data collected in free-living conditions on people with T1D. This is particularly significant in the context of automated glucose control systems for diabetes, in that the methods we propose have the potential to inform changes in treatment parameters in response to the intensity of physical activity, allowing patients to meet their glycemic targets.

Physical Activity and Psychological Stress Detection and Assessment of Their Effects on Glucose Concentration Predictions in Diabetes Management

OBJECTIVE

Continuous glucose monitoring (CGM) enables prediction of the future glucose concentration (GC) trajectory for making informed diabetes management decisions. The glucose concentration values are affected by various physiological and metabolic variations, such as physical activity (PA) and acute psychological stress (APS), in addition to meals and insulin. In this work, we extend our adaptive glucose modeling framework to incorporate the effects of PA and APS on the GC predictions.

METHODS

A wristband conducive of use by free-living ambulatory people is used. The measured physiological variables are analyzed to generate new quantifiable input features for PA and APS. Machine learning techniques estimate the type and intensity of the PA and APS when they occur individually and concurrently. Variables quantifying the characteristics of both PA and APS are integrated as exogenous inputs in an adaptive system identification technique for enhancing the accuracy of GC predictions. Data from clinical experiments illustrate the improvement in GC prediction accuracy.

RESULTS

The average mean absolute error (MAE) of one-hour-ahead GC predictions with testing data decreases from 35.1 to 31.9 mg/dL (p-value = 0.01) with the inclusion of PA information, and it decreases from 16.9 to 14.2 mg/dL (p-value = 0.006) with the inclusion of PA and APS information.

CONCLUSION

The first-ever glucose prediction model is developed that incorporates measures of physical activity and acute psychological stress to improve GC prediction accuracy.

SIGNIFICANCE

Modeling the effects of physical activity and acute psychological stress on glucose concentration values will improve diabetes management and enable informed meal, activity and insulin dosing decisions.

Long-term use of the hybrid artificial pancreas by adjusting carbohydrate ratios and programmed basal rate: A reinforcement learning approach

BACKGROUND AND OBJECTIVES

The hybrid artificial pancreas regulates glucose levels in people with type 1 diabetes. It delivers (i) insulin boluses at meal times based on the meals' carbohydrate content and the carbohydrate ratios (CRs) and (ii) insulin basal, between meals and at night, continuously modulated around individual-specific programmed basal rate. The CRs and programmed basal rate significantly vary between individuals and within the same individual with type 1 diabetes, and using suboptimal values in the hybrid artificial pancreas may degrade glucose control. We propose a reinforcement learning algorithm to adaptively optimize CRs and programmed basal rate to improve the performance of the hybrid artificial pancreas.

METHODS

The proposed reinforcement learning algorithm was designed using the Q-learning approach. The algorithm learns the optimal actions (CRs and programmed basal rate) by applying them to the individual's state (previous day's glucose levels and insulin delivery) based on an exploration and exploitation trade-off. First, outcomes from our simulator were compared to those of a clinical study in 23 individuals with type 1 diabetes and have yielded similar results. Second, the learning algorithm was tested using the simulator with two scenarios. Scenario 1 has fixed meal sizes and ingestion times and scenario 2 has a more realistic eating behavior with random meal sizes, ingestion times, and carbohydrate counting errors.

RESULTS

After about five weeks, the reinforcement learning algorithm improved the percentage of time spent in target range from 67% to 86.7% in scenario 1 and 65.5% to 86% in scenario 2. The percentage of time spent below 4.0 mmol/L decreased from 9% to 0.9% in scenario 1 and 9.5% to 1.1% in scenario 2.

CONCLUSIONS

Results indicate that the proposed algorithm has the potential to improve glucose control in people with type 1 diabetes using the hybrid artificial pancreas. The proposed algorithm is a key in making the hybrid artificial pancreas adaptive for the long-term real life outpatient studies.

Toward a Fully Automated Artificial Pancreas System Using a Bioinspired Reinforcement Learning Design: In Silico Validation

OBJECTIVE

The automation of insulin treatment is the most challenge aspect of glucose management for type 1 diabetes owing to unexpected exogenous events (e.g., meal intake). In this article, we propose a novel reinforcement learning (RL) based artificial intelligence (AI) algorithm for a fully automated artificial pancreas (AP) system.

METHODS

A bioinspired RL designing method was developed for automated insulin infusion. This method has reward functions that imply the temporal homeostatic objective and discount factors that reflect an individual specific pharmacological characteristic. The proposed method was applied to a training method using an RL algorithm and was evaluated in virtual patients from the FDA approved UVA/Padova simulator with unannounced meal intakes.

RESULTS

For a single-meal experiment with preprandial fasting, the trained policy demonstrated fully automated regulation in both the basal and postprandial phases. In the in silico trial with a variation of insulin sensitivity and dawn phenomenon, the policy achieved a mean glucose of 124.72 mg/dL and percentage time in the normal range of 89.56%. The layer-wise relevance propagation provides interpretable information on AI-driven decision for robustness to sensor noise, automated postprandial regulation, and insulin stacking avoidance.

CONCLUSION

The AP algorithm based on the bioinspired RL approach enables fully automated blood glucose control with unannounced meal intake.

SIGNIFICANCE

The proposed framework can be extended to other drug-based treatments for systems with significant uncertainties.

Determining Physical Activity Characteristics from Wristband Data for Use in Automated Insulin Delivery Systems

Algorithms that can determine the type of physical activity (PA) and quantify the intensity can allow precision medicine approaches, such as automated insulin delivery systems that modulate insulin administration in response to PA. In this work, data from a multi-sensor wristband is used to design classifiers to distinguish among five different physical states (PS) (resting, activities of daily living, running, biking, and resistance training), and to develop models to estimate the energy expenditure (EE) of the PA for diabetes therapy. The data collected are filtered, features are extracted from the reconciled signals, and the extracted features are used by machine learning algorithms, including deep-learning techniques, to obtain accurate PS classification and EE estimation. The various machine learning techniques have different success rates ranging from 75.7% to 94.8% in classifying the five different PS. The deep neural network model with long short-term memory has 94.8% classification accuracy. We achieved 0.5 MET (Metabolic Equivalent of Task) root-mean-square error for EE estimation accuracy, relative to indirect calorimetry with randomly selected testing data (10% of collected data). We also demonstrate a 5% improvement in PS classification accuracy and a 0.34 MET decrease in the mean absolute error when using multi-sensor approach relative to using only accelerometer data.

Improving blood glucose level predictability using machine learning

This study was designed to improve blood glucose level predictability and future hypoglycemic and hyperglycemic event alerts through a novel patient-specific supervised-machine-learning (SML) analysis of glucose level based on a continuous-glucose-monitoring system (CGM) that needs no human intervention, and minimises false-positive alerts. The CGM data over 7 to 50 non-consecutive days from 11 type-1 diabetic patients aged 18 to 39 with a mean HbA1C of 7.5% ± 1.2% were analysed using four SML models. The algorithm was constructed to choose the best-fit model for each patient. Several statistical parameters were calculated to aggregate the magnitudes of the prediction errors. The personalised solutions provided by the algorithm were effective in predicting glucose levels 30 minutes after the last measurement. The average root-mean-square-error was 20.48 mg/dL and the average absolute-mean-error was 15.36 mg/dL when the best-fit model was selected for each patient. Using the best-fit-model, the true-positive-hypoglycemia-prediction-rate was 64%, whereas the false-positive- rate was 4.0%, and the false-negative-rate was 0.015%. Similar results were found even when only CGM samples below 70 were considered. The true-positive-hyperglycemia-prediction-rate was 61%. State-of-the-art SML tools are effective in predicting the glucose level values of patients with type-1diabetes and notifying these patients of future hypoglycemic and hyperglycemic events, thus improving glycemic control. The algorithm can be used to improve the calculation of the basal insulin rate and bolus insulin, and suitable for a closed loop "artificial pancreas" system. The algorithm provides a personalised medical solution that can successfully identify the best-fit method for each patient.

Model free sliding mode controller for blood glucose control: Towards artificial pancreas without need to mathematical model of the system

BACKGROUND

The mechanism of glucose regulation in human blood is a nonlinear complicated biological system with uncertain parameters and external disturbances which cannot be imitated accurately by a simple mathematical model. So to achieve an artificial pancreas, a method that does not need a model is necessary.

METHODS

In this paper, a model free third order terminal sliding mode controller is developed and applied to blood glucose regulation system. So in this paper, a data driven control method is proposed which doesn't need a pre specified mathematical model of the system. The proposed method uses a third order terminal sliding mode controller to overcome the problem in finite time without chattering. It also uses a disturbance estimation technique to reject external disturbances. The sliding mode algorithm is equipped with a regression algorithm to release its need to model of the system. It is proved theoretically that the method is stable and the error converges to zero. In order to determine the parameters needed in this method, an algorithm is provided.

RESULTS

Simulation studies are carried out with different scenarios and compared with Model Free Adaptive Control method. At the first scenario, the proposed method is applied to a virtual type- 1 diabetic patient without considering of external disturbances. The blood glucose level of 110 mg/dl is considered as the goal and it is illustrated that the desired glucose concentration is obtained. It is illustrated that the proposed method shows better performance against Model Free Adaptive Controller. Then in the next scenario, blood glucose of the patient is controlled in presence of three meal times during a day with different values of carbohydrate. The maximum of the blood glucose in this scenario is obtained as 168.5 mg/dl and the minimum of it stays on 85.5 Mg/dl. So the patient blood glucose level is almost within acceptable range (70-180 mg/dl) unlike the Model Free Adaptive Controller. In the last scenario, 22 tests are done for different patients (by randomly varying simulator parameters in ± 40% range) and the control performance is evaluated by the well-known Control Variability Grid Analysis CVGA. For all of them, the blood glucose remains in the green zone (safe region) of the CVGA .

CONCLUSION

Simulation results show that the proposed method acts robustly and can overcome uncertainties and external disturbances. The blood glucose level remains in safe region in all case. So the proposed method can be used in an artificial pancreas.

In-Silico Evaluation of Glucose Regulation Using Policy Gradient Reinforcement Learning for Patients with Type 1 Diabetes Mellitus

In this paper, we test and evaluate policy gradient reinforcement learning for automated blood glucose control in patients with Type 1 Diabetes Mellitus. Recent research has shown that reinforcement learning is a promising approach to accommodate the need for individualized blood glucose level control algorithms. The motivation for using policy gradient algorithms comes from the fact that adaptively administering insulin is an inherently continuous task. Policy gradient algorithms are known to be superior in continuous high-dimensional control tasks. Previously, most of the approaches for automated blood glucose control using reinforcement learning has used a finite set of actions. We use the Trust-Region Policy Optimization algorithm in this work. It represents the state of the art for deep policy gradient algorithms. The experiments are carried out in-silico using the Hovorka model, and stochastic behavior is modeled through simulated carbohydrate counting errors to illustrate the full potential of the framework. Furthermore, we use a model-free approach where no prior information about the patient is given to the algorithm. Our experiments show that the reinforcement learning agent is able to compete with and sometimes outperform state-of-the-art model predictive control in blood glucose regulation.

A Data-Driven Personalized Model of Glucose Dynamics Taking Account of the Effects of Physical Activity for Type 1 Diabetes: An In Silico Study

This paper aims to develop a data-driven model for glucose dynamics taking into account the effects of physical activity (PA) through a numerical study. It intends to investigate PA's immediate effect on insulin-independent glucose variation and PA's prolonged effect on insulin sensitivity. We proposed a nonlinear model with PA (NLPA), consisting of a linear regression of PA and a bilinear regression of insulin and PA. The model was identified and evaluated using data generated from a physiological PA-glucose model by Dalla Man et al. integrated with the uva/padova Simulator. Three metrics were computed to compare blood glucose (BG) predictions by NLPA, a linear model with PA (LPA), and a linear model with no PA (LOPA). For PA's immediate effect on glucose, NLPA and LPA showed 45-160% higher mean goodness of fit (FIT) than LOPA under 30 min-ahead glucose prediction (P < 0.05). For the prolonged PA effect on glucose, NLPA showed 87% higher FIT than LPA (P < 0.05) for simulations using no previous measurements. NLPA had 25-37% and 31-54% higher sensitivity in predicting postexercise hypoglycemia than LPA and LOPA, respectively. This study demonstrated the following qualitative trends: (1) for moderate-intensity exercise, accuracy of BG prediction was improved by explicitly accounting for PA's effect; and (2) accounting for PA's prolonged effect on insulin sensitivity can increase the chance of early prediction of postexercise hypoglycemia. Such observations will need to be further evaluated through human subjects in the future.

Control-Oriented Model With Intra-Patient Variations for an Artificial Pancreas

In this work, a low-order model designed for glucose regulation in Type 1 Diabetes Mellitus (T1DM) is obtained from the UVA/Padova metabolic simulator. It captures not only the nonlinear behavior of the glucose-insulin system, but also intra-patient variations related to daily insulin sensitivity ( S_I) changes. To overcome the large inter-subject variability, the model can also be personalized based on a priori patient information. The structure is amenable for linear parameter varying (LPV) controller design, and represents the dynamics from the subcutaneous insulin input to the subcutaneous glucose output. The efficacy of this model is evaluated in comparison with a previous control-oriented model which in turn is an improvement of previous models. Both models are compared in terms of their open- and closed-loop differences with respect to the UVA/Padova model. The proposed model outperforms previous T1DM control-oriented models, which could potentially lead to more robust and reliable controllers for glycemia regulation.

Online Glucose Prediction Using Computationally Efficient Sparse Kernel Filtering Algorithms in Type-1 Diabetes

Streaming data from continuous glucose monitoring (CGM) systems enable the recursive identification of models to improve estimation accuracy for effective predictive glycemic control in patients with type-1 diabetes. A drawback of conventional recursive identification techniques is the increase in computational requirements, which is a concern for online and real-time applications such as the artificial pancreas systems implemented on handheld devices and smartphones where computational resources and memory are limited. To improve predictions in such computationally constrained hardware settings, efficient adaptive kernel filtering algorithms are developed in this paper to characterize the nonlinear glycemic variability by employing a sparsification criterion based on the information theory to reduce the computation time and complexity of the kernel filters without adversely deteriorating the predictive performance. Furthermore, the adaptive kernel filtering algorithms are designed to be insensitive to abnormal CGM measurements, thus compensating for measurement noise and disturbances. As such, the sparsification-based real-time model update framework can adapt the prediction models to accurately characterize the time-varying and nonlinear dynamics of glycemic measurements. The proposed recursive kernel filtering algorithms leveraging sparsity for improved computational efficiency are applied to both in-silico and clinical subjects, and the results demonstrate the effectiveness of the proposed methods.

Realizing a Closed-Loop (Artificial Pancreas) System for the Treatment of Type 1 Diabetes

Recent, rapid changes in the treatment of type 1 diabetes have allowed for commercialization of an "artificial pancreas" that is better described as a closed-loop controller of insulin delivery. This review presents the current state of closed-loop control systems and expected future developments with a discussion of the human factor issues in allowing automation of glucose control. The goal of these systems is to minimize or prevent both short-term and long-term complications from diabetes and to decrease the daily burden of managing diabetes. The closed-loop systems are generally very effective and safe at night, have allowed for improved sleep, and have decreased the burden of diabetes management overnight. However, there are still significant barriers to achieving excellent daytime glucose control while simultaneously decreasing the burden of daytime diabetes management. These systems use a subcutaneous continuous glucose sensor, an algorithm that accounts for the current glucose and rate of change of the glucose, and the amount of insulin that has already been delivered to safely deliver insulin to control hyperglycemia, while minimizing the risk of hypoglycemia. The future challenge will be to allow for full closed-loop control with minimal burden on the patient during the day, alleviating meal announcements, carbohydrate counting, alerts, and maintenance. The human factors involved with interfacing with a closed-loop system and allowing the system to take control of diabetes management are significant. It is important to find a balance between enthusiasm and realistic expectations and experiences with the closed-loop system.

Simulation Software for Assessment of Nonlinear and Adaptive Multivariable Control Algorithms: Glucose - Insulin Dynamics in Type 1 Diabetes

A simulator for testing automatic control algorithms for nonlinear systems with time-varying parameters, variable time delays, and uncertainties is developed. It is based on simulation of virtual patients with Type 1 diabetes (T1D). Nonlinear models are developed to describe glucose concentration (GC) variations based on user-defined scenarios for meal consumption, insulin administration, and physical activity. They compute GC values and physiological variables, such as heart rate, skin temperature, accelerometer, and energy expenditure, that are indicative of physical activities affecting GC dynamics. This is the first simulator designed for assessment of multivariable controllers that consider supplemental physiological variables in addition to GC measurements to improve glycemic control. Virtual patients are generated from distributions of identified model parameters using clinical data. The simulator will enable testing and evaluation of new control algorithms proposed for automated insulin delivery as well as various control algorithms for nonlinear systems with uncertainties, time-varying parameters and delays.

Hypoglycemia Prevention via Personalized Glucose-Insulin Models Identified in Free-Living Conditions

BACKGROUND

The objective of this research is to show the effectiveness of individualized hypoglycemia predictive alerts (IHPAs) based on patient-tailored glucose-insulin models (PTMs) for different subjects. Interpatient variability calls for PTMs that have been identified from data collected in free-living conditions during a one-month trial.

METHODS

A new impulse-response (IR) identification technique has been applied to free-living data in order to identify PTMs that are able to predict the future glucose trends and prevent hypoglycemia events. Impulse response has been applied to seven patients with type 1 diabetes (T1D) of the University of Amsterdam Medical Centre. Individualized hypoglycemia predictive alert has been designed for each patient thanks to the good prediction capabilities of PTMs.

RESULTS

The PTMs performance is evaluated in terms of index of fitting (FIT), coefficient of determination, and Pearson's correlation coefficient with a population FIT of 63.74%. The IHPAs are evaluated on seven patients with T1D with the aim of predicting in advance (between 45 and 10 minutes) the unavoidable hypoglycemia events; these systems show better performance in terms of sensitivity, precision, and accuracy with respect to previously published results.

CONCLUSION

The proposed work shows the successful results obtained applying the IR to an entire set of patients, participants of a one-month trial. Individualized hypoglycemia predictive alerts are evaluated in terms of hypoglycemia prevention: the use of a PTM allows to detect 84.67% of the hypoglycemia events occurred during a one-month trial on average with less than 0.4% of false alarms. The promising prediction capabilities of PTMs can be a key ingredient for new generations of individualized model predictive control for artificial pancreas.

Blood glucose regulation in type 1 diabetic patients: an adaptive parametric compensation control-based approach

Here, a direct adaptive control strategy with parametric compensation is adopted for an uncertain non‐linear model representing blood glucose regulation in type 1 diabetes mellitus patients. The uncertain parameters of the model are updated by appropriate design of adaptation laws using the Lyapunov method. The closed‐loop response of the plasma glucose concentration as well as external insulin infusion rate is analysed for a wide range of variation of the model parameters through extensive simulation studies. The result indicates that the proposed adaptive control scheme avoids severe hypoglycaemia and gives satisfactory performance under parametric uncertainty highlighting its ability to address the issue of inter‐patient variability.

Plasma-Insulin-Cognizant Adaptive Model Predictive Control for Artificial Pancreas Systems

An adaptive model predictive control (MPC) algorithm with dynamic adjustments of constraints and objective function weights based on estimates of the plasma insulin concentration (PIC) is proposed for artificial pancreas (AP) systems. A personalized compartment model that translates the infused insulin into estimates of PIC is integrated with a recursive subspace-based system identification to characterize the transient dynamics of glycemic measurements. The system identification approach is able to identify stable, reliable linear time-varying models from closed-loop data. An MPC algorithm using the adaptive models is designed to compute the optimal exogenous insulin delivery for AP systems without requiring any manually-entered meal information. A dynamic safety constraint derived from the estimation of PIC is incorporated in the adaptive MPC to improve the efficacy of the AP and prevent insulin overdosing. Simulation case studies demonstrate the performance of the proposed adaptive MPC algorithm.

Model individualization for artificial pancreas

BACKGROUND AND OBJECTIVE

The inter-subject variability characterizing the patients affected by type 1 diabetes mellitus makes automatic blood glucose control very challenging. Different patients have different insulin responses, and a control law based on a non-individualized model could be ineffective. The definition of an individualized control law in the context of artificial pancreas is currently an open research topic. In this work we consider two novel identification approaches that can be used for individualizing linear glucose-insulin models to a specific patient.

METHODS

The first approach belongs to the class of black-box identification and is based on a novel kernel-based nonparametric approach, whereas the second is a gray-box identification technique which relies on a constrained optimization and requires to postulate a model structure as prior knowledge. The latter is derived from the linearization of the average nonlinear adult virtual patient of the UVA/Padova simulator. Model identification and validation are based on in silico data collected during simulations of clinical protocols designed to produce a sufficient signal excitation without compromising patient safety. The identified models are evaluated in terms of prediction performance by means of the coefficient of determination, fit, positive and negative max errors, and root mean square error.

RESULTS

Both identification approaches were used to identify a linear individualized glucose-insulin model for each adult virtual patient of the UVA/Padova simulator. The resulting model simulation performance is significantly improved with respect to the performance achieved by a linear average model.

CONCLUSIONS

The approaches proposed in this work have shown a good potential to identify glucose-insulin models for designing individualized control laws for artificial pancreas.

Multivariable Artificial Pancreas for Various Exercise Types and Intensities

BACKGROUND

Exercise challenges people with type 1 diabetes in controlling their glucose concentration (GC). A multivariable adaptive artificial pancreas (MAAP) may lessen the burden.

METHODS

The MAAP operates without any user input and computes insulin based on continuous glucose monitor and physical activity signals. To analyze performance, 18 60-h closed-loop experiments with 96 exercise sessions with three different protocols were completed. Each day, the subjects completed one resistance and one treadmill exercise (moderate continuous training [MCT] or high-intensity interval training [HIIT]). The primary outcome is time spent in each glycemic range during the exercise + recovery period. Secondary measures include average GC and average change in GC during each exercise modality.

RESULTS

The GC during exercise + recovery periods were within the euglycemic range (70-180 mg/dL) for 69.9% of the time and within a safe glycemic range for exercise (70-250 mg/dL) for 93.0% of the time. The exercise sessions are defined to begin 30 min before the start of exercise and end 2 h after start of exercise. The GC were within the severe hypoglycemia (<55 mg/dL), moderate hypoglycemia (55-70 mg/dL), moderate hyperglycemia (180-250 mg/dL), and severe hyperglycemia (>250 mg/dL) for 0.9%, 1.3%, 23.1%, and 4.8% of the time, respectively. The average GC decline during exercise differed with exercise type (P = 0.0097) with a significant difference between the MCT and resistance (P = 0.0075). To prevent large GC decreases leading to hypoglycemia, MAAP recommended carbohydrates in 59% of MCT, 50% of HIIT, and 39% of resistance sessions.

CONCLUSIONS

A consistent GC decline occurred in exercise and recovery periods, which differed with exercise type. The average GC at the start of exercise was above target (185.5 ± 56.6 mg/dL for MCT, 166.9 ± 61.9 mg/dL for resistance training, and 171.7 ± 41.4 mg/dL HIIT), making a small decrease desirable. Hypoglycemic events occurred in 14.6% of exercise sessions and represented only 2.22% of the exercise and recovery period.

Incorporating Unannounced Meals and Exercise in Adaptive Learning of Personalized Models for Multivariable Artificial Pancreas Systems

BACKGROUND

Despite the recent advancements in the modeling of glycemic dynamics for type 1 diabetes mellitus, automatically considering unannounced meals and exercise without manual user inputs remains challenging.

METHOD

An adaptive model identification technique that incorporates exercise information and estimates of the effects of unannounced meals obtained automatically without user input is proposed in this work. The effects of the unknown consumed carbohydrates are estimated using an individualized unscented Kalman filtering algorithm employing an augmented glucose-insulin dynamic model, and exercise information is acquired from noninvasive physiological measurements. The additional information on meals and exercise is incorporated with personalized estimates of plasma insulin concentration and glucose measurement data in an adaptive model identification algorithm.

RESULTS

The efficacy of the proposed personalized and adaptive modeling algorithm is demonstrated using clinical data involving closed-loop experiments of the artificial pancreas system, and the results demonstrate accurate glycemic modeling with the average root-mean-square error (mean absolute error) of 25.50 mg/dL (18.18 mg/dL) for six-step (30 minutes ahead) predictions.

CONCLUSIONS

The approach presented is able to identify reliable time-varying individualized glucose-insulin models.

Adaptive Zone Model Predictive Control of Artificial Pancreas Based on Glucose- and Velocity-Dependent Control Penalties

OBJECTIVE

Zone model predictive control (MPC) has been proven to be an efficient approach to closed-loop insulin delivery in clinical studies. In this paper, we aim to safely reduce mean glucose levels by proposing control penalty adaptation in the cost function of zone MPC.

METHODS

A zone MPC method with a dynamic cost function that updates its control penalty parameters in real time according to the predicted glucose and its rate of change is developed. The proposed method is evaluated on the entire 100-adult cohort of the FDA-accepted UVA/Padova T1DM simulator and compared with the zone MPC tested in an extended outpatient study.

RESULTS

For unannounced meals, the proposed method leads to statistically significant improvements in terms of mean glucose (153.8 mg/dL vs. 159.0 mg/dL; ) and percentage time in [70, 180] mg/dL ([Formula: see text] vs. [Formula: see text]; ) without increasing the risk of hypoglycemia. Performance for announced meals is similar to that obtained without adaptation. The proposed method also behaves properly and safely for scenarios of moderate meal-bolus and basal rate mismatches, as well as simulated unannounced exercise. Advisory-mode analysis based on clinical data indicates that the method can reduce glucose levels through suggesting additional safe amounts of insulin on top of those suggested by the zone MPC used in the study.

CONCLUSION

The proposed method leads to improved glucose control without increasing hypoglycemia risks.

SIGNIFICANCE

The results validate the feasibility of improving glucose regulation through glucose- and velocity-dependent control penalty adaptation in MPC design.

Short-term prediction of glucose in type 1 diabetes using kernel adaptive filters

This study aims at presenting a nonlinear, recursive, multivariate prediction model of the subcutaneous glucose concentration in type 1 diabetes. Nonlinear regression is performed in a reproducing kernel Hilbert space, by either the fixed budget quantized kernel least mean square (QKLMS-FB) or the approximate linear dependency kernel recursive least-squares (KRLS-ALD) algorithm, such that a sparse model structure is accomplished. A multivariate feature set (i.e., subcutaneous glucose, food carbohydrates, insulin regime and physical activity) is used and its influence on short-term glucose prediction is investigated. The method is evaluated using data from 15 patients with type 1 diabetes in free-living conditions. In the case when all the input variables are considered: (i) the average root mean squared error (RMSE) of QKLMS-FB increases from 13.1 mg dL^-1 (mean absolute percentage error (MAPE) 6.6%) for a 15-min prediction horizon (PH) to 37.7 mg dL^-1 (MAPE 20.8%) for a 60-min PH and (ii) the RMSE of KRLS-ALD, being predictably lower, increases from 10.5 mg dL^-1 (MAPE 5.2%) for a 15-min PH to 31.8 mg dL^-1 (MAPE 18.0%) for a 60-min PH. Multivariate data improve systematically both the regularity and the time lag of the predictions, reducing the errors in critical glucose value regions for a PH ≥ 30 min. Graphical abstract ᅟ.

Evaluation of an Artificial Pancreas with Enhanced Model Predictive Control and a Glucose Prediction Trust Index with Unannounced Exercise

BACKGROUND

We investigated the safety and efficacy of the addition of a trust index to enhanced Model Predictive Control (eMPC) Artificial Pancreas (AP) that works by adjusting the responsiveness of the controller's insulin delivery based on the confidence intervals around predictions of glucose trends. This constitutes a dynamic adaptation of the controller's parameters in contrast with the widespread AP implementation of individualized fixed controller tuning.

MATERIALS AND METHODS

After 1 week of sensor-augmented pump (SAP) use, subjects completed a 48-h AP admission that included three meals/day (carbohydrate range 29-57 g/meal), a 1-h unannounced brisk walk, and two overnight periods. Endpoints included sensor glucose percentage time 70-180, <70, >180 mg/dL, number of hypoglycemic events, and assessment of the trust index versus standard eMPC glucose predictions.

RESULTS

Baseline characteristics for the 15 subjects who completed the study (mean ± SD) were age 46.1 ± 17.8 years, HbA1c 7.2% ± 1.0%, diabetes duration 26.8 ± 17.6 years, and total daily dose (TDD) 35.5 ± 16.4 U/day. Mean sensor glucose percent time 70-180 mg/dL (88.0% ± 8.0% vs. 74.6% ± 9.4%), <70 mg/dL (1.5% ± 1.9% vs. 7.8% ± 6.0%), and number of hypoglycemic events (0.6 ± 0.6 vs. 6.3 ± 3.4), all showed statistically significant improvement during AP use compared with the SAP run-in (P < 0.001). On average, the trust index enhanced controller responsiveness to predicted hyper- and hypoglycemia by 26% (P < 0.005).

CONCLUSIONS

In this population of well-controlled patients, we conclude that eMPC with trust index AP achieved nearly 90% time in the target glucose range. Additional studies will further validate these results.

Velocity-weighting & velocity-penalty MPC of an artificial pancreas: Improved safety & performance

A novel Model Predictive Control (MPC) law for the closed-loop operation of an Artificial Pancreas (AP) to treat type 1 diabetes is proposed. The contribution of this paper is to simultaneously enhance both the safety and performance of an AP, by reducing the incidence of controller-induced hypoglycemia, and by promoting assertive hyperglycemia correction. This is achieved by integrating two MPC features separately introduced by the authors previously to independently improve the control performance with respect to these two coupled issues. Velocity-weighting MPC reduces the occurrence of controller-induced hypoglycemia. Velocity-penalty MPC yields more effective hyperglycemia correction. Benefits of the proposed MPC law over the MPC strategy deployed in the authors' previous clinical trial campaign are demonstrated via a comprehensive in-silico analysis. The proposed MPC law was deployed in four distinct US Food & Drug Administration approved clinical trial campaigns, the most extensive of which involved 29 subjects each spending three months in closed-loop. The paper includes implementation details, an explanation of the state-dependent cost functions required for velocity-weighting and penalties, a discussion of the resulting nonlinear optimization problem, a description of the four clinical trial campaigns, and control-related trial highlights.

Multi-level Supervision and Modification of Artificial Pancreas Control System

Artificial pancreas (AP) systems provide automated regulation of blood glucose concentration (BGC) for people with type 1 diabetes (T1D). An AP includes three components: a continuous glucose monitoring (CGM) sensor, a controller calculating insulin infusion rate based on the CGM signal, and a pump delivering the insulin amount calculated by the controller to the patient. The performance of the AP system depends on successful operation of these three components. Many APs use model predictive controllers that rely on models to predict BGC and to calculate the optimal insulin infusion rate. The performance of model-based controllers depends on the accuracy of the models that is affected by large dynamic changes in glucose-insulin metabolism or equipment performance that may move the operating conditions away from those used in developing the models and designing the control system. Sensor errors and missing signals will cause calculation of erroneous insulin infusion rates. And the performance of the controller may vary at each sampling step and each period (meal, exercise, and sleep), and from day to day. Here we describe a multi-level supervision and controller modification (ML-SCM) module is developed to supervise the performance of the AP system and retune the controller. It supervises AP performance in 3 time windows: sample level, period level, and day level. At sample level, an online controller performance assessment sub-module will generate controller performance indexes to evaluate various components of the AP system and conservatively modify the controller. A sensor error detection and signal reconciliation module will detect sensor error and reconcile the CGM sensor signal at each sample. At period level, the controller performance is evaluated with information collected during a certain time period and the controller is tuned more aggressively. At the day level, the daily CGM ranges are further analyzed to determine the adjustable range of controller parameters used for sample level and period level. Thirty subjects in the UVa/Padova metabolic simulator were used to evaluate the performance of the ML-SCM module and one clinical experiment is used to illustrate its performance in a clinical environment. The results indicate that the AP system with an ML-SCM module has a safer range of glucose concentration distribution and more appropriate insulin infusion rate suggestions than an AP system without the ML-SCM module.

Automatic Detection and Estimation of Unannounced Meals for Multivariable Artificial Pancreas System

BACKGROUND

Automatically attenuating the postprandial rise in the blood glucose concentration without manual meal announcement is a significant challenge for artificial pancreas (AP) systems. In this study, a meal module is proposed to detect the consumption of a meal and to estimate the amount of carbohydrate (CHO) intake.

METHODS

The meals are detected based on qualitative variables describing variation of continuous glucose monitoring (CGM) readings. The CHO content of the meals/snacks is estimated by a fuzzy system using CGM and subcutaneous insulin delivery data. The meal bolus amount is computed according to the patient's insulin to CHO ratio. Integration of the meal module into a multivariable AP system allows revision of estimated CHO based on knowledge about physical activity, sleep, and the risk of hypoglycemia before the final decision for a meal bolus is made.

RESULTS

The algorithm is evaluated by using 117 meals/snacks in retrospective data from 11 subjects with type 1 diabetes. Sensitivity, defined as the percentage of correctly detected meals and snacks, is 93.5% for meals and 68.0% for snacks. The percentage of false positives, defined as the proportion of false detections relative to the total number of detected meals and snacks, is 20.8%.

CONCLUSIONS

Integration of a meal detection module in an AP system is a further step toward an automated AP without manual entries. Detection of a consumed meal/snack and infusion of insulin boluses using an estimate of CHO enables the AP system to automatically prevent postprandial hyperglycemia.

Model-Fusion-Based Online Glucose Concentration Predictions in People with Type 1 Diabetes

Accurate predictions of glucose concentrations are necessary to develop an artificial pancreas (AP) system for people with type 1 diabetes (T1D). In this work, a novel glucose forecasting paradigm based on a model fusion strategy is developed to accurately characterize the variability and transient dynamics of glycemic measurements. To this end, four different adaptive filters and a fusion mechanism are proposed for use in the online prediction of future glucose trajectories. The filter fusion mechanism is developed based on various prediction performance indexes to guide the overall output of the forecasting paradigm. The efficiency of the proposed model fusion based forecasting method is evaluated using simulated and clinical datasets, and the results demonstrate the capability and prediction accuracy of the data-based fusion filters, especially in the case of limited data availability. The model fusion framework may be used in the development of an AP system for glucose regulation in patients with T1D.

Multivariable Adaptive Artificial Pancreas System in Type 1 Diabetes

PURPOSE OF REVIEW

The review summarizes the current state of the artificial pancreas (AP) systems and introduces various new modules that should be included in future AP systems.

RECENT FINDINGS

A fully automated AP must be able to detect and mitigate the effects of meals, exercise, stress and sleep on blood glucose concentrations. This can only be achieved by using a multivariable approach that leverages information from wearable devices that provide real-time streaming data about various physiological variables that indicate imminent changes in blood glucose concentrations caused by meals, exercise, stress and sleep. The development of a fully automated AP will necessitate the design of multivariable and adaptive systems that use information from wearable devices in addition to glucose sensors and modify the models used in their model-predictive alarm and control systems to adapt to the changes in the metabolic state of the user. These AP systems will also integrate modules for controller performance assessment, fault detection and diagnosis, machine learning and classification to interpret various signals and achieve fault-tolerant control. Advances in wearable devices, computational power, and safe and secure communications are enabling the development of fully automated multivariable AP systems.

Non-linear dynamic modeling of glucose in type 1 diabetes with kernel adaptive filters

We propose a non-linear recursive solution to the problem of short-term prediction of glucose in type 1 diabetes. The Fixed Budget Quantized Kernel Least Mean Square (QKLMS-FB) algorithm is employed to construct a univariate model of subcutaneous glucose concentration, which: (i) handles nonlinearities by transforming the input space into a high-dimensional Reproducing Kernel Hilbert Space and, (ii) finds a sparse solution by retaining a representative subset of the training input vectors. The dataset comes from the continuous multi-day recordings of 15 type 1 patients in free-living conditions. QKLMS-FB produces an average root mean squared error of 18.66±3.19 mg/dl for a prediction horizon of 30 min with 82.04% of hypoglycemic readings and 93.30% of hyperglycemic ones being classified as clinically accurate or with benign errors. The effect of the prediction horizon is more evident in the hypoglycemic range.

Personalization of a compartmental physiological model for an artificial pancreas through integration of patient's state estimation

Artificial Pancreas (AP) are developed for patients with Type 1 diabetes. This medical device system consists in the association of a subcutaneous continuous glucose monitor (CGM) providing a proxy of the patient's glycaemia and a control algorithm offering the real-time modification of the insulin delivery with an automatic command of the subcutaneous insulin pump. The most complex algorithms are based on a compartmental model of the glucoregulatory system of the patient coupled to an approach of MPC (Model-Predictive-Control) for the command. The automatic and unsupervised control of insulin regulation constitutes a major challenge in AP projects. A given model with its parameterization on the shelf will not directly represent the patient's data behavior and the personalization of the model is a prerequisite before using it in a MPC. The present paper focuses on the personalization of a compartmental showing a method where taking into account the estimation of the patient's state in addition to the parameter estimation improves the results in terms of mean quadratic error.

A review of personalized blood glucose prediction strategies for T1DM patients

This paper presents a methodological review of models for predicting blood glucose (BG) concentration, risks and BG events. The surveyed models are classified into three categories, and they are presented in summary tables containing the most relevant data regarding the experimental setup for fitting and testing each model as well as the input signals and the performance metrics. Each category exhibits trends that are presented and discussed. This document aims to be a compact guide to determine the modeling options that are currently being exploited for personalized BG prediction.

Use of Wearable Sensors and Biometric Variables in an Artificial Pancreas System

An artificial pancreas (AP) computes the optimal insulin dose to be infused through an insulin pump in people with Type 1 Diabetes (T1D) based on information received from a continuous glucose monitoring (CGM) sensor. It has been recognized that exercise is a major challenge in the development of an AP system. The use of biometric physiological variables in an AP system may be beneficial for prevention of exercise-induced challenges and better glucose regulation. The goal of the present study is to find a correlation between biometric variables such as heart rate (HR), heat flux (HF), skin temperature (ST), near-body temperature (NBT), galvanic skin response (GSR), and energy expenditure (EE), 2D acceleration-mean of absolute difference (MAD) and changes in glucose concentrations during exercise via partial least squares (PLS) regression and variable importance in projection (VIP) in order to determine which variables would be most useful to include in a future artificial pancreas. PLS and VIP analyses were performed on data sets that included seven different types of exercises. Data were collected from 26 clinical experiments. Clinical results indicate ST to be the most consistently important (important for six out of seven tested exercises) variable over all different exercises tested. EE and HR are also found to be important variables over several types of exercise. We also found that the importance of GSR and NBT observed in our experiments might be related to stress and the effect of changes in environmental temperature on glucose concentrations. The use of the biometric measurements in an AP system may provide better control of glucose concentration.

Hypoglycemia Detection and Carbohydrate Suggestion in an Artificial Pancreas

Fear of hypoglycemia is a major concern for many patients with type 1 diabetes and affects patient decisions for use of an artificial pancreas system. We propose an alternative way for prevention of hypoglycemia by issuing predictive hypoglycemia alarms and encouraging patients to consume carbohydrates in a timely manner. The algorithm has been tested on 6 subjects (3 males and 3 females, age 24.2 ± 4.5 years, weight 79.2 ± 16.2 kg, height 172.7 ± 9.4 cm, HbA1C 7.3 ± 0.48%, duration of diabetes 209.2 ± 87.9 months) over 3-day closed-loop clinical experiments as part of a multivariable artificial pancreas control system. Over 6 three-day clinical experiments, there were only 5 real hypoglycemia episodes, of which only 1 hypoglycemia episode occurred due to being missed by the proposed algorithm. The average hypoglycemia alarms per day and per subject was 3. Average glucose value when the first alarms were triggered was recorded to be 117 ± 30.6 mg/dl. Average carbohydrate consumption per alarm was 14 ± 7.8 grams. Our results have shown that most low glucose concentrations can be predicted in advance and the glucose levels can be raised back to the desired levels by consuming an appropriate amount of carbohydrate. The proposed algorithm is able to prevent most hypoglycemic events by suggesting appropriate levels of carbohydrate consumption before the actual occurrence of hypoglycemia.

Online prediction of glucose concentration in type 1 diabetes using extreme learning machines

We propose an online machine-learning solution to the problem of nonlinear glucose time series prediction in type 1 diabetes. Recently, extreme learning machine (ELM) has been proposed for training single hidden layer feed-forward neural networks. The high accuracy and fast learning speed of ELM drive us to investigate its applicability to the glucose prediction problem. Given that diabetes self-monitoring data are received sequentially, we focus on online sequential ELM (OS-ELM) and online sequential ELM kernels (KOS-ELM). A multivariate feature set is utilized concerning subcutaneous glucose, insulin therapy, carbohydrates intake and physical activity. The dataset comes from the continuous multi-day recordings of 15 type 1 patients in free-living conditions. Assuming stationarity and evaluating the performance of the proposed method by 10-fold cross- validation, KOS-ELM were found to perform better than OS-ELM in terms of prediction error, temporal gain and regularity of predictions for a 30-min prediction horizon.

Impact of Type 1 Diabetes Technology on Family Members/Significant Others of People With Diabetes

BACKGROUND

The aim was to explore the impact of diabetes-related technology to ensure that such devices are used in a way that returns maximum benefit from a medical and psychological perspective.

METHOD

Spouses and caregivers of people with type 1 diabetes were invited to complete an online questionnaire about their experiences with diabetes technologies used by their family members. Participants were recruited via the Glu online community website. Questions explored impact on daily living, frequency and severity of hypoglycemia, and diabetes-related distress.

RESULTS

In all, 100 parents/caregivers and 74 partners participated in this survey. Average (mean) duration of living with a person with type 1 diabetes was 16 years (SD = 13) for partners, with duration of diabetes for children being 4.2 ± 3.2 years. Average duration of current therapy was 8.3 ± 7.3 years for adults and 3.4 ± 2.9 years for children. Of the participants, 86% partners and 82% parents/caregivers reported diabetes technology had made it easier for their family members to achieve blood glucose targets. Compared to partners, parents/caregivers reported more negative emotions (P < .001) and decreased well-being (P < .001) related to their family members type 1 diabetes. Diabetes-related distress was common, as was sleep disturbance associated with device alarms and fear of hypoglycemia. Reduced frequency and severity of hypoglycemia related to device use was reported by approximately half of participants.

CONCLUSION

There is little doubt about the medical benefit of diabetes technologies and their uptake is increasing but some downsides were reported. Barriers to uptake of technologies lie beyond the mechanics of diabetes management. Supporting users in using diabetes technology to achieve the best possible glycemic control, in the context of their own life, is crucial. Furthermore, understanding these issues with input from the type 1 diabetes community including family members and caregivers will help innovation and design of new technology.